def test_runtime_limit_hor(self):
import time
planned_pipeline = (MinMaxScaler | Normalizer) >> LinearRegression
from sklearn.datasets import load_boston
X, y = load_boston(return_X_y=True)
max_opt_time = 3.0
hor = GridSearchCV(
estimator=planned_pipeline,
cv=3,
max_opt_time=max_opt_time,
scoring="r2",
)
start = time.time()
with self.assertRaises(BaseException):
_ = hor.fit(X[:500, :], y[:500])
end = time.time()
opt_time = end - start
rel_diff = (opt_time - max_opt_time) / max_opt_time
assert (
rel_diff < 0.2
), "Max time: {}, Actual time: {}, relative diff: {}".format(
max_opt_time, opt_time, rel_diff
)
def test_runtime_limit_hoc(self):
import time
planned_pipeline = (MinMaxScaler | Normalizer) >> (
LogisticRegression | KNeighborsClassifier)
from sklearn.datasets import load_iris
X, y = load_iris(return_X_y=True)
max_opt_time = 10.0
hoc = GridSearchCV(
estimator=planned_pipeline,
cv=3,
scoring="accuracy",
max_opt_time=max_opt_time,
)
start = time.time()
with self.assertRaises(BaseException):
_ = hoc.fit(X, y)
end = time.time()
opt_time = end - start
rel_diff = (opt_time - max_opt_time) / max_opt_time
assert (rel_diff < 0.7
), "Max time: {}, Actual time: {}, relative diff: {}".format(
max_opt_time, opt_time, rel_diff)
def test_with_sklearn_gridsearchcv(self):
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score, make_scorer
from sklearn.model_selection import GridSearchCV
lr = LogisticRegression()
parameters = {"solver": ("liblinear", "lbfgs"), "penalty": ["l2"]}
with warnings.catch_warnings():
warnings.simplefilter("ignore")
clf = GridSearchCV(
lr, parameters, cv=5, scoring=make_scorer(accuracy_score)
)
iris = load_iris()
clf.fit(iris.data, iris.target)
def test_with_gridsearchcv_auto_wrapped_pipe1(self):
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score, make_scorer
lr = LogisticRegression()
pca = PCA()
trainable = pca >> lr
with warnings.catch_warnings():
warnings.simplefilter("ignore")
from lale.lib.lale import GridSearchCV
clf = GridSearchCV(
estimator=trainable, lale_num_samples=1, lale_num_grids=1,
cv=2, scoring=make_scorer(accuracy_score))
iris = load_iris()
clf.fit(iris.data, iris.target)
def test_grid_search_on_trained_auto(self):
from sklearn.metrics import accuracy_score, make_scorer
from sklearn.model_selection import GridSearchCV
iris = load_iris()
X, y = iris.data, iris.target
lr = LogisticRegression()
trained = lr.fit(X, y)
parameters = get_grid_search_parameter_grids(lr, num_samples=2)
_ = GridSearchCV(trained, parameters, cv=5, scoring=make_scorer(accuracy_score))
def test_grid_search_on_trained(self):
from sklearn.metrics import accuracy_score, make_scorer
from sklearn.model_selection import GridSearchCV
iris = load_iris()
X, y = iris.data, iris.target
lr = LogisticRegression()
trained = lr.fit(X, y)
parameters = {"solver": ("liblinear", "lbfgs"), "penalty": ["l2"]}
_ = GridSearchCV(trained, parameters, cv=5, scoring=make_scorer(accuracy_score))
def test_manual_grid(self):
from lale.lib.sklearn import SVC
from sklearn.datasets import load_iris
from lale.lib.lale import GridSearchCV
warnings.simplefilter("ignore")
from lale import wrap_imported_operators
wrap_imported_operators()
iris = load_iris()
parameters = {'kernel': ('linear', 'rbf'), 'C': [1, 10]}
svc = SVC()
clf = GridSearchCV(estimator=svc, param_grid=parameters)
clf.fit(iris.data, iris.target)
clf.predict(iris.data)
